Why augmentation multiplies training data in Computer Vision - Quick Recap

Recall & Review

beginner

What is data augmentation in computer vision?

Data augmentation is a technique that creates new training images by applying simple changes like rotation, flipping, or color shifts to existing images. This helps the model learn better by seeing more varied examples.

beginner

Why does augmentation multiply the amount of training data?

Because each original image can be changed in many ways, augmentation creates many new images from one. This increases the total number of training examples, helping the model learn more patterns.

intermediate

How does augmentation help prevent overfitting?

By showing the model many different versions of images, augmentation stops the model from memorizing exact images. Instead, the model learns general features that work well on new, unseen images.

beginner

Name three common augmentation techniques used in computer vision.

Common techniques include flipping images horizontally, rotating images by small angles, and changing brightness or colors slightly.

beginner

What is the main benefit of multiplying training data with augmentation?

The main benefit is that the model gets more diverse examples to learn from, which improves its ability to recognize objects in different situations and reduces errors on new images.

What does data augmentation do to training images?

A Deletes half of the images to reduce size

B Creates new images by modifying existing ones

C Converts images to black and white only

D Copies images without any changes

Data augmentation creates new images by applying changes like rotation or flipping to existing images.

Why is multiplying training data helpful for a model?

A It helps the model learn more varied examples

B It makes the model run faster

C It reduces the number of classes

D It removes noise from images

More varied examples help the model learn better and generalize to new data.

Which of these is NOT a common augmentation technique?

A Adding random noise to labels

B Rotating images slightly

C Flipping images horizontally

D Changing image brightness

Adding noise to labels is not an image augmentation technique.

How does augmentation reduce overfitting?

A By removing hard examples from training

B By decreasing the number of training images

C By simplifying the model architecture

D By increasing data variety so the model doesn't memorize exact images

Augmentation increases variety, helping the model learn general features instead of memorizing.

If you have 100 images and apply 3 different augmentations, how many images do you have for training?

A 100

B 300

C 400

D 600

Original 100 images plus 3 augmentations each (3 x 100 = 300) equals 400 images total.

Explain in your own words why data augmentation multiplies training data in computer vision.

Think about how one photo can become many different photos by small changes.

Describe how multiplying training data with augmentation helps reduce overfitting.

Consider why seeing many versions of the same object helps the model.

Practice

1. Why does image augmentation multiply the training data in computer vision?

easy

A. Because it creates new images by changing existing ones

B. Because it deletes some images to reduce overfitting

C. Because it compresses images to save space

D. Because it labels images automatically

Solution

1. Step 1: Understand augmentation purpose

   Augmentation creates new images by applying changes like rotation or flipping to existing images.

2. Step 2: Connect augmentation to data size

   These new images increase the total number of training samples, effectively multiplying the dataset size.

3. Final Answer:

   Because it creates new images by changing existing ones -> Option A

4. Quick Check:

   Augmentation = new image versions [OK]

Hint: Augmentation makes new images from old ones [OK]

Common Mistakes:

• Thinking augmentation deletes images
• Confusing augmentation with compression
• Believing augmentation automatically labels data

2. Which of the following Python code snippets correctly applies horizontal flip augmentation using torchvision transforms?

easy

A. transform = transforms.FlipHorizontal()

B. transform = transforms.HorizontalFlip()

C. transform = transforms.RandomHorizontalFlip(p=1.0)

D. transform = transforms.RandomFlip(direction='horizontal')

Solution

1. Step 1: Recall torchvision syntax

   In torchvision, horizontal flip is done with RandomHorizontalFlip and a probability parameter.

2. Step 2: Check options for correct class and parameters

   Only transform = transforms.RandomHorizontalFlip(p=1.0) uses the correct class name and parameter format.

3. Final Answer:

   transform = transforms.RandomHorizontalFlip(p=1.0) -> Option C

4. Quick Check:

   Correct torchvision flip syntax = transform = transforms.RandomHorizontalFlip(p=1.0) [OK]

Hint: Look for RandomHorizontalFlip with p parameter [OK]

Common Mistakes:

• Using incorrect class names like HorizontalFlip
• Missing the probability parameter p
• Assuming FlipHorizontal exists in torchvision

3. Given this code snippet applying augmentation, what is the total number of images after augmentation if the original dataset has 100 images and each image is augmented with 3 different transformations?

medium

A. 300

B. 400

C. 100

D. 600

Solution

1. Step 1: Calculate augmented images per original

   Each original image produces 3 new augmented images plus the original itself, totaling 4 images per original.

2. Step 2: Multiply by original dataset size

   100 original images * 4 images each = 400 images total after augmentation.

3. Final Answer:

   400 -> Option B

4. Quick Check:

   (3 augmentations + 1 original) * 100 = 400 [OK]

Hint: Add original + augmentations, then multiply by dataset size [OK]

Common Mistakes:

• Counting only augmented images, ignoring originals
• Multiplying by 3 instead of 4
• Adding instead of multiplying

4. Identify the error in this augmentation code snippet and select the fix:

from torchvision import transforms
transform = transforms.Compose([
    transforms.RandomRotation(30),
    transforms.RandomFlip(horizontal=true)
])

medium

A. Replace RandomFlip with RandomHorizontalFlip

B. Change RandomRotation(30) to RandomRotation(degrees=30)

C. Add p=0.5 to RandomFlip

D. No error, code is correct

Solution

1. Step 1: Check torchvision augmentation classes

   There is no RandomFlip class in torchvision; horizontal flip uses RandomHorizontalFlip.

2. Step 2: Identify correct fix

   Replacing RandomFlip with RandomHorizontalFlip fixes the error; other options are incorrect or unnecessary.

3. Final Answer:

   Replace RandomFlip with RandomHorizontalFlip -> Option A

4. Quick Check:

   Correct flip class = RandomHorizontalFlip [OK]

Hint: Use exact torchvision class names for flips [OK]

Common Mistakes:

• Assuming RandomFlip exists
• Changing rotation syntax unnecessarily
• Adding parameters to non-existent classes

5. You have a small dataset of 50 images. You want to multiply your training data by 5 times using augmentation. Which combination of augmentations is best to achieve this without losing original images?

hard

A. Apply 5 augmentations but discard original images

B. Only keep original images and train longer

C. Apply 2 augmentations and duplicate images twice

D. Apply 4 different augmentations per image plus keep original images

Solution

1. Step 1: Understand multiplication goal

   To multiply data by 5 times, total images after augmentation should be 50 * 5 = 250.

2. Step 2: Calculate images per original

   Keeping original plus 4 augmentations per image gives 5 images per original, totaling 250 images.

3. Step 3: Evaluate options

   Apply 4 different augmentations per image plus keep original images achieves the goal without losing original images; others either discard originals or don't reach 5x.

4. Final Answer:

   Apply 4 different augmentations per image plus keep original images -> Option D

5. Quick Check:

   Original + 4 augmentations = 5x data [OK]

Hint: Keep originals + 4 augmentations for 5x data [OK]

Common Mistakes:

• Discarding original images reduces data size
• Duplicating images without augmentation doesn't add variety
• Training longer without augmentation doesn't multiply data